A deep learning model for predicting mechanical properties of polycrystalline graphene

Molecular dynamics simulations have been widely used to understand the properties of nanomaterials. The main issue associated with molecular dynamic modeling is the high computational costs. Machine learning (ML) models can be used as an alternative method for predicting the behavior of materials. After training, machine learning models can provide instantaneous results and avoid the computational costs of molecular dynamic simulations. We develop a deep convolutional neural network model to predict the mechanical properties of polycrystalline graphene. The data required for training our machine learning model is generated using molecular dynamics simulations by modeling the behavior of polycrystalline graphene under uniaxial tensile loading. More than 2000 data points are generated for graphene sheets of different grain sizes and grain orientations. The goal is to train the network such that it can predict the Young's modulus and fracture stress of graphene sheets by analyzing an image of the polycrystalline sheet.